Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/drag88/claude-dev-framework/taskgit clone --depth 1 https://github.com/drag88/claude-dev-frameworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.00862 |
| Opus 5 | $0.00006 | $0.00431 |
| Sonnet 5 | $0.00002 | $0.00172 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cdf:task — Task Execution
Execute defined tasks with structured delegation when fan-out is warranted. For multi-step work, write a clear prompt and let Claude plan — orchestration scaffolding has been removed in favor of native planning.
Quick Start
/cdf:task create "enterprise authentication system"
/cdf:task execute "feature backlog" --delegate --parallel
/cdf:task --breakdown "implement user authentication system"
When to Use
- Task requires fan-out across multiple subagents working in parallel
- You want a documented delegation contract (tools whitelist + scope boundaries) for each subagent
- Long-running work where state persistence matters
For single-subagent work or simple sequential steps, just write the prompt — Claude plans that well from a clear prompt at high effort.
Delegation contract (when fanning out)
When invoking the Task tool, include these seven sections so the subagent has everything it needs in one turn:
### 1. Task
Atomic, specific goal — one action only.
### 2. Expected outcome
Concrete deliverables with measurable success criteria.
### 3. Required skills
Which CDF skill or agent to invoke (e.g. "codebase-navigator", "library-researcher").
### 4. Required tools
Explicit tool whitelist (e.g. "Read, Grep, Glob"). No tools outside this list.
### 5. Required actions
- Each requirement on its own line
- Be specific and actionable
- Reference real file paths and patterns
### 6. Out of scope
- Forbidden actions
- Scope boundaries
- Quality constraints
### 7. Context
- File paths: relevant paths
- Patterns: naming conventions, code patterns
- Constraints: time, scope, dependencies
Skeleton
### 1. Task
<one atomic goal>
### 2. Expected outcome
<deliverables and success criteria>
### 3. Required skills
<skill or agent name>
### 4. Required tools
<explicit tool whitelist>
### 5. Required actions
<one requirement per line>
### 6. Out of scope
<forbidden actions and boundaries>
### 7. Context
<file paths, patterns, constraints>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 119 lines · 12 tokens per session scan A 32c547809655
task is a command published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 862 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.